Ankit15nov/setfit-ethos-multilabel-example

SetFit with sentence-transformers/paraphrase-mpnet-base-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-mpnet-base-v2 as the Sentence Transformer embedding model. A OneVsRestClassifier instance is used for classification.

The model has been trained using an efficient few-shot learning technique that involves:

1. Fine-tuning a Sentence Transformer with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.

Model Details

Model Description

• Model Type: SetFit
• Sentence Transformer body: sentence-transformers/paraphrase-mpnet-base-v2
• Classification head: a OneVsRestClassifier instance
• Maximum Sequence Length: 512 tokens

Model Sources

• Repository: SetFit on GitHub
• Paper: Efficient Few-Shot Learning Without Prompts
• Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts

Evaluation

Metrics

Label	Accuracy
all	0.2754

Uses

Direct Use for Inference

First install the SetFit library:

pip install setfit

Then you can load this model and run inference.

from setfit import SetFitModel

# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("Ankit15nov/setfit-ethos-multilabel-example")
# Run inference
preds = model("NiSource Inc. NYSE NI completes the issuance of a 19.9 indirect equity interest in NIPSCO to Blackstone Infrastructure Partners affiliate for 2.16 billion with an additional equity commitment of 250 million. The investment aims to strengthen NIPSCO's financial foundation support sustainable long term growth and fund ongoing capital requirements for energy transition and reindustrialization of the Midwest. ")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	2	590.5	2491

Training Hyperparameters

• batch_size: (4, 4)
• num_epochs: (1, 1)
• max_steps: -1
• sampling_strategy: oversampling
• num_iterations: 20
• body_learning_rate: (2e-05, 2e-05)
• head_learning_rate: 2e-05
• loss: CosineSimilarityLoss
• distance_metric: cosine_distance
• margin: 0.25
• end_to_end: False
• use_amp: False
• warmup_proportion: 0.1
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0018	1	0.4292	-
0.0893	50	0.0057	-
0.1786	100	0.2115	-
0.2679	150	0.0003	-
0.3571	200	0.0022	-
0.4464	250	0.0003	-
0.5357	300	0.0083	-
0.625	350	0.0043	-
0.7143	400	0.0038	-
0.8036	450	0.0014	-
0.8929	500	0.0031	-
0.9821	550	0.0014	-

Framework Versions

• Python: 3.10.14
• SetFit: 1.0.3
• Sentence Transformers: 2.7.0
• Transformers: 4.40.1
• PyTorch: 2.1.0
• Datasets: 2.3.2
• Tokenizers: 0.19.1

Citation

BibTeX

@article{https://doi.org/10.48550/arxiv.2209.11055,
    doi = {10.48550/ARXIV.2209.11055},
    url = {https://arxiv.org/abs/2209.11055},
    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {Efficient Few-Shot Learning Without Prompts},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}